© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89769
    Prev
    Next
    INDEX
    Explanations

    runes should

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    1.10
    r
    0.81
    at
    0.80
    к
    0.79
    <0x0D>
    0.77
    i
    0.76
    ر
    0.67
    क
    0.64
    션
    0.64
     phosphorylation
    0.63
    POSITIVE LOGITS
     be
    0.86
    ní
    0.76
    峣
    0.75
     페
    0.74
     mittler
    0.74
    俻
    0.73
     był
    0.73
    ają
    0.72
    İ
    0.71
     the
    0.71
    Activations Density 0.003%

    No Known Activations